| ZERO Lab

Optimization-induced Implicit Graph Diffusion. ICML, 2022.

Due to the over-smoothing issue, most existing graph neural networks can only capture limited de- pendencies with their inherently …

Qi Chen , Yifei Wang , Yisen Wang , Jiansheng Yang , Zhouchen Lin

PDF

Training Much Deeper Spiking Neural Networks with a Small Number of Time-Steps. Neural Networks, 2022.

Spiking Neural Network (SNN) is a promising energy-efficient neural architecture when implemented on neuromorphic hardware. The …

Qingyan Meng , Shen Yan , Mingqing Xiao , Yisen Wang , Zhouchen Lin , Zhi-Quan Luo

PDF

Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation. CVPR, 2022.

Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. However, it is a …

Qingyan Meng , Mingqing Xiao , Shen Yan , Yisen Wang , Zhouchen Lin , Zhi-Quan Luo

PDF Code

Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State. NeurIPS, 2021.

Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. However, …

Mingqing Xiao , Qingyan Meng , Zongpeng Zhang , Yisen Wang , Zhouchen Lin

PDF Code

Reparameterized Sampling for Generative Adversarial Networks. ECML-PKDD, 2021.

Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs). …

Yifei Wang , Yisen Wang , Jiansheng Yang , Zhouchen Lin

PDF

Demystifying Adversarial Training via A Unified Probabilistic Framework. ICML workshop 2021, 2021.

Adversarial Training (AT) is known as an effective approach to enhance the robustness of deep neural networks. Recently researchers …

Yifei Wang , Yisen Wang , Jiansheng Yang , Zhouchen Lin

PDF

Dissecting the Diffusion Process in Linear Graph Convolutional Networks. NeurIPS, 2021.

Graph Convolutional Networks (GCNs) have attracted more and more attentions in recent years. A typical GCN layer consists of a linear …

Yifei Wang , Yisen Wang , Jiansheng Yang , Zhouchen Li

PDF

Efficient Equivariant Network. NeurIPS, 2021.

Convolutional neural networks (CNNs) have dominated the field of Computer Vision and achieved great success due to their built-in …

Lingshen He , Yuxuan Chen , Zhenyang Shen , Yiming Dong , Yisen Wang , Zhouchen Lin

PDF

Gauge Equivariant Transformer. NeurIPS, 2021.

Attention mechanism has shown great performance and efficiency in a lot of deep learning models, in which relative position encoding …

Lingshen He , Yiming Dong , Yisen Wang , Dacheng Tao , Zhouchen Lin

PDF

Residual Relaxation for Multi-view Representation Learning. NeurIPS, 2021.

Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the …

Yifei Wang , Zhengyang Geng , Feng Jiang , Chuming Li , Yisen Wang , Jiansheng Yang , Zhouchen Li

PDF

Improving Adversarial Robustness via Channel-wise Activation Suppressing. ICLR, 2021.

The study of adversarial examples and their activations have attracted significant attention for secure and robust learning with deep …

Yang Bai , Yuyuan Zeng , Yong Jiang , Shu-Tao Xia , Xingjun Ma , Yisen Wang

PDF

Towards A Unified Understanding and Improving of Adversarial Transferability. ICLR, 2021.

In this paper, we use the interaction inside adversarial perturbations to explain and boost the adversarial transferability. We …

Xin Wang , Jie Ren , Shuyun Lin , Xiangming Zhu , Yisen Wang , Quanshi Zhang

PDF

Unlearnable Examples: Making Personal Data Unexploitable. ICLR, 2021.

The volume of “free” data on the internet has been key to the current success of deep learning. However, it also raises …

Hanxun Huang , Xingjun Ma , Sarah Monazam Erfani , James Bailey , Yisen Wang

PDF

Adversarial Weight Perturbation Helps Robust Generalization. NeurIPS, 2020.

The study on improving the robustness of deep neural networks against adversarial examples grows rapidly in recent years. Among them, …

Dongxian Wu , Shu-Tao Xia , Yisen Wang

PDF

Normalized Loss Functions for Deep Learning with Noisy Labels. ICML, 2020.

Robust loss functions are essential for training accurate deep neural networks (DNNs) in the presence of noisy (incorrect) labels. It …

Xingjun Ma , Hanxun Huang , Yisen Wang , Simone Romano , Sarah Erfani , James Bailey

PDF Code

Improving Adversarial Robustness Requires Revisiting Misclassified Examples. ICLR, 2020.

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by imperceptible perturbations. A range of defense …

Yisen Wang , Difan Zou , Jinfeng Yi , James Bailey , Xingjun Ma , Quanquan Gu

PDF Code

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets. ICLR, 2020.

Skip connections are an essential component of current state-of-the-art deep neural networks (DNNs) such as ResNet, WideResNet, …

Dongxian Wu , Yisen Wang , Shu-Tao Xia , James Bailey , Xingjun Ma

PDF Code

Symmetric Cross Entropy for Robust Learning with Noisy Labels. ICCV, 2019.

Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of …

Yisen Wang , Xingjun Ma , Zaiyi Chen , Yuan Luo , Jinfeng Yi , James Bailey

PDF Code

On the Convergence and Robustness of Adversarial Training. ICML, 2019.

Improving the robustness of deep neural networks (DNNs) to adversarial examples is an important yet challenging problem for secure deep …

Yisen Wang , Xingjun Ma , James Bailey , Jinfeng Yi , Bowen Zhou , Quanquan Gu

PDF Code

Yisen Wang

Assistant Professor

Peking University

Personal Site

Biography

Selected Publications

Optimization-induced Implicit Graph Diffusion. ICML, 2022.

Training Much Deeper Spiking Neural Networks with a Small Number of Time-Steps. Neural Networks, 2022.

Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation. CVPR, 2022.

Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State. NeurIPS, 2021.

Reparameterized Sampling for Generative Adversarial Networks. ECML-PKDD, 2021.

Demystifying Adversarial Training via A Unified Probabilistic Framework. ICML workshop 2021, 2021.

Dissecting the Diffusion Process in Linear Graph Convolutional Networks. NeurIPS, 2021.

Efficient Equivariant Network. NeurIPS, 2021.

Gauge Equivariant Transformer. NeurIPS, 2021.

Residual Relaxation for Multi-view Representation Learning. NeurIPS, 2021.

Improving Adversarial Robustness via Channel-wise Activation Suppressing. ICLR, 2021.

Towards A Unified Understanding and Improving of Adversarial Transferability. ICLR, 2021.

Unlearnable Examples: Making Personal Data Unexploitable. ICLR, 2021.

Adversarial Weight Perturbation Helps Robust Generalization. NeurIPS, 2020.

Normalized Loss Functions for Deep Learning with Noisy Labels. ICML, 2020.

Improving Adversarial Robustness Requires Revisiting Misclassified Examples. ICLR, 2020.

Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets. ICLR, 2020.

Symmetric Cross Entropy for Robust Learning with Noisy Labels. ICCV, 2019.

On the Convergence and Robustness of Adversarial Training. ICML, 2019.

Awards

ACM China Doctoral Dissertation Nomination Award (Nation-wide Top 5)

Tsinghua University Outstanding Doctoral Dissertation Award

Baidu Scholarship (World-wide Top 10)

Microsoft Research Fellowship Nomination Award

Best Paper Award